Tag
Meta 的 IdeaScientist 论文将科研构思拆解为缺口发现、创新与报告撰写三个角色并分别用强化学习训练，基于 Qwen3.6-27B 在 2.77M 理念语料库上检索，超越最强开源 autoresearch 基线 14.0%，并优于 Claude Code SDK 与 Codex SDK 方案最多 5.9%。
Researchers introduce EPOCH, an evidence-governed architecture for AI research agents that combines task contracts, typed memory, active falsification, and independent replay, achieving state-of-the-art performance on AlgoTune (0.65 vs 0.53 mean normalized score) and the Math14 suite.
The article critiques the mislabeling of chatbots like ChatGPT as AI research agents, arguing that true research agents must handle complex, multi-step workflows. It features 'mira ai science' as a tool that attempts to meet these needs.